Access to this full-text is provided by Wiley.
Content available from Computational Intelligence and Neuroscience
This content is subject to copyright. Terms and conditions apply.
Research Article
Application of Visual Sensing Techniques in Computational
Intelligence for Risk Assessment of Sports Injuries in Colleges
Yan Sun,
1
Yang Zheng,
2
Le He,
1
Liang Guo,
1
and Xiao Geng
1
1
Department of Physical Education, Chang’an University, Xi’an, Shaanxi 710064, China
2
School of Humanity, Chang’an University, Xi’an, Shaanxi 710064, China
Correspondence should be addressed to Xiao Geng; tendenr@chd.edu.cn
Received 29 December 2021; Revised 20 January 2022; Accepted 26 January 2022; Published 22 April 2022
Academic Editor: Rahim Khan
Copyright ©2022 Yan Sun et al. is is an open access article distributed under the Creative Commons Attribution License, which
permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Injury prediction is one of the most challenging issues in sports and is a key component of injury prevention, since successful
injury prediction forms the basis for effective preventive measures. In this study, an analysis was made on the risk of physical
injuries to college students to guarantee the physical safety of students in sports and improve the quality of physical education.
en, a study was carried out on the occurrences of physical injury risks through visual sensing techniques, and an investigation
was conducted into the characteristics of physical injury risks in colleges. Next, the student’s body shape and physical char-
acteristics are computed using visual sensing techniques, and the risk of sports injuries is evaluated. e results show that the
proposed image recognition and computation methods can accurately identify the sports injuries of college students. Fur-
thermore, it can effectively analyze the factors affecting the risk of sports injuries, and the error of the proposed technique remains
between −3 and 2. In addition, it can accurately locate the occurrence of sports injury risks and reduce the impact of those risks in
time. is work provides technical support for the reduction of sports injury risks and contributes to the improvement of physical
education teaching quality in colleges.
1. Introduction
Physical education in college has positive effects on health
during adolescence. In addition to physical health benefits,
physically-active students tend to have better psychological
health than their classmates, reporting fewer symptoms of
depression, more confidence, self-emotional control, greater
social well-being, and higher levels of life satisfaction.
Participation in sports also contributes to character devel-
opment, reducing risk behaviors, improving school per-
formance, and promoting public engagement [1]. Long-term
benefits of PE may continue into adulthood, as students who
are involved in sports activities may be more likely than their
peers to be physically active. However, sports participation
may also increase the risk of injuries that cause short-term or
long-term disability. Sports injuries are common in younger
students. More than 3.4 million teenagers are injured as part
of organized sports each year. One-third of all injuries in
children are related to sports, too. e most common sports
injuries in children are strains and sprains. Contact sports,
such as football and basketball, account for more injuries
than noncontact sports, such as running and swimming [2].
To reduce the risk of injuries, the development of college
PE is an important link in the development of sports.
Presently, college PE is of great significance in enhancing
students’ physical and psychological health. College PE de-
velops students’ confidence and competence to participate in
several physical activities that become a dominant part of their
lives, both in and out of school [3]. A high-quality PE cur-
riculum enables students to develop different skills and the
ability to use strategies and compositional ideas to perform
successfully. As a result, they develop the confidence to
participate in different physical activities and studies about
the value of healthy, active lifestyles. However, because the PE
teaching model is different from the traditional teaching
methods, there are still many problems in college PE teaching,
especially the physical safety of college students in physical
education, which needs to be improved [4].
Hindawi
Computational Intelligence and Neuroscience
Volume 2022, Article ID 9080661, 9 pages
https://doi.org/10.1155/2022/9080661
Many scholars have conducted comprehensive research
on the assessment of injuries in college physical education.
Zhou [5] pointed out that the college PE curriculum plays a
very important role in college education, and PE teaching
evaluation is the decisive factor for the improvement of
physical education. erefore, to reduce physical injuries
and enhance the effects of PE, an important way is to im-
prove the teaching evaluation of college PE. Zadeh et al. [6]
predicted that the PE teaching model in the 21st century was
still a pattern of coexistence of multiple modes. is di-
versified pattern was conducive to giving full play to stu-
dents’ subjective initiative, enhancing students’ sports
awareness, and cultivating students’ interest in physical
education. Moreover, it will become the main mode of
college physical education in China in the 21st century. Zhou
[7] revealed that given the problems of physical injuries in
the existing college PE program, the way of reform is to
change the traditional teaching methods and to realize the
sports effect from students’ awareness of their physical
characteristics. Hulme and Finch [8] found that a combi-
nation of high body mass index (BMI) and high mechanical
loads could result in injury. erefore, in creating a physical
exercise program, it is essential to incrementally increase
mechanical load through the practice season as athletes
become conditioned. Rao [9] proposed a dynamic, recursive
model for risk assessment and causes of sports injuries and
proposed that the injury has a nonlinear behavior. is
model is helpful in the understanding of sports injury eti-
ology because it proposes that there may be recurrent
changes in susceptibility to injury along with the partici-
pation in sports, and the primary risk factors’ exposure can
produce adaptations and continuously change the risk.
Eetvelde [10] has proposed a paradigm shift in sports injuries
and emphasized that the literature is limited to consistently
identifying predictive factors because current research
methods based on unidirectional and logical approaches
ignore the factors and complex conditions for sports injury
emergence. To reduce sports injuries, Yi and Fang [11]
presented a method based on functional motion biological
image data and summarized the mistakes and deficits of
common movement patterns of athletes and proposed
various intervention procedures to improve the effect of
sports injury assessment. Jinhai [12] proposed that the
machine learning method in combination with image
processing can be used to identify athletes at high injury risk
during sports participation and to identify risk factors.
However, most of the earliest studies did not apply machine
learning methods accurately to predict injuries, and the
methodological study quality was moderate to very low.
In this study, a deep perception is implemented on the
current situation of college PE. An analysis was made on the
risks of sports injuries. en the potential sports injuries of
college students are pointed out to verify the impact of sports
injury risks. Furthermore, the college students’ body shapes
and characteristics of sports injury risks are identified and
computed using visual sensing techniques. In addition, an
analysis is made on the influencing factors of sports injury risks
in colleges, as well as a comprehensive evaluation and technical
support is provided for the reforms of college sports education.
e rest of the manuscript is organized as follows: in
Section 2, an overview of sports injuries is provided and the
proposed visual sensing technique is presented. Section 3 is
about the analysis of the visual sensing techniques. e
results are illustrated in Sections 4, and Section 5 is about the
conclusion.
2. Methods
2.1. Sports Injuries in Physical Education. Injuries are
common in college sports and have significant physical,
psychosocial, and economic consequences. Exploring the
injury risk factors and their relationship is thus a crucial
component of preventing future injuries in sports [13].
Sports injuries are the results of complex interactions of
various risk factors and provoking events making a com-
prehensive model necessary. Owing to the interactions
between extrinsic and intrinsic risk factors as well as their
unpredictable nature, the ability to predict the occurrence of
an injury event is highly challenging. One of the ultimate
tasks in college PE is to prevent the risks that high-intensity
physical education will cause to students. ese risks refer to
the physical and psychological injuries that students may
suffer in the process of physical education [14]. is study
evaluates the risk of sports injury in colleges through
computational intelligence and visual sensing techniques,
and reduces the risk through evaluation, to ensure the long-
term development of PE in colleges.
Sports injuries occur during exercise or while participating
in a sport. Students are particularly at risk for these types of
injuries. Morphological and behavioral characteristics are the
most intuitive external manifestations of human body injuries
and are important indicators for the evaluation of human
health. When predicting human body injuries without contact,
the commonly used method is to obtain the image of the
human body via infrared-based visual sensing equipment in
computational intelligence, and then identify and judge the
surface shape of the human body through computation and
analysis so that physical safety can be guaranteed for college
students in sports. Besides, the risks in the process of PE can be
reduced [15]. Figure 1 demonstrates the prediction process of
risks to college students in PE through visual sensing tech-
niques in computational intelligence.
Figure 1 reveals that, in the process of physical injury risk
assessment for students, what needs to be done initially is to
collect information about the physical body shape of stu-
dents through image acquisition technology. e collected
image information is subsequently sent to a processing
system. en, the collected images are processed using
different image processing techniques. A comprehensive
analysis is conducted on the processed images to evaluate the
analyzed images and obtain the results.
2.2. Computational Intelligent Vision Sensing Algorithm.
When the collected image is input into the computer system, it
needs to be processed using visual sensing techniques. After
processing, the image can be analyzed and evaluated. In the
process of image processing, it is necessary to analyze the gray
2Computational Intelligence and Neuroscience
level of image pixels. Because the equipment in the process of
image acquisition has different color recognition mechanisms
from human vision, it is necessary to describe the image in
terms of RGB (red, green, blue) and HIS (hue, intensity,
saturation) color modes in the computer system. e pro-
cessed image can be more consistent with human visual
characteristics. Moreover, the HIS color mode in computer
image processing can greatly reduce the task of image pro-
cessing. e difference between RGB color mode and HIS
color mode only lies in the difference in representation
methods of the same physical quantity, so they need to be
computed and converted. Equations (1)–(3) are the calcula-
tions when the light source of the collected image is white [16].
H�0.620.170.18 �R, (1)
S�00.0661.02 �G, (2)
I�0.310.590.11 �B, (3)
where Hrepresents the hue, Srefers to the saturation, and I
stands for the intensity. e terms R, G, and Bindicate the
red, green, and blue, respectively, and ·bespeaks the gradient
transformation. e calculated image is a gray-level image,
which is composed of black and white in human vision. In
image analysis, it is also necessary to smooth the collected
infrared scanning images to eliminate the image noise, keep
the image smooth, reduce the abrupt gradient, and com-
prehensively improve the image quality [17]. It can be
computed as
gi�Med fi−v. . . fi. . . fi+v
v�m−1
2,(4)
where girepresents the filtered value of the image and Med
indicates the ordered median. Equation (5) indicates the
calculation method for smoothing the two-dimensional
image.
gθ�Med xij
,(5)
where gθrepresents the filtered value of a two-dimensional
image. en, in the process of image acquisition, the hier-
archical scene of the collected image may be reduced or
blurred due to too much brightness or insufficient bright-
ness. erefore, it is necessary to adjust the contrast of an
image to restore the normal visual effect [18], as shown in the
following equation:
g�T(f).(6)
After transformation, the contrast of the processed
image can be obtained as
g(x, y) � T[f(x, y)],(7)
where g(x, y)represents the contrast of the processed image
and f(x, y)refers to the contrast of the original image. If the
contrast of the input image is set as f(x, y)and distributed
in [a, b], the contrast of the output image is g(x, y), dis-
tributed in [m, n], and the relationship between them is
linear which can be represented as
g(x, y) �
m, f(x, y)<a,
n−m
b−a[f(x, y) − a] + m, a ≤f(x, y)≤b,
n, f(x, y)>b.
⎧
⎪
⎪
⎪
⎪
⎪
⎪
⎪
⎨
⎪
⎪
⎪
⎪
⎪
⎪
⎪
⎩
(8)
e collected image mainly includes the target image of
the background. In the analysis process, the target image
needs to be extracted; that is, the image is separated to identify
Comprehensive
Image Processing
Result
Appearance Image Analysis Appearance Image
Acquisition
Infrared Image Analysis Infrared Image
Acquisition
Athlete
Transmission
Figure 1: Risk assessment of physical education students by visual sensing techniques.
Computational Intelligence and Neuroscience 3
the main target image. To achieve this goal, the gray level of
the collected image needs to be defined, and the background
and target image are separated through the difference in gray
value [19], as shown in the following equation:
g(x, y) � 1, f(x, y)≥T,
0, f(x, y)<T,
(9)
where 1 and 0 are the pixel distinction between the back-
ground and the target image and Tϵ[n1, n2]. e basic
principle is to divide the contrast of two images according to
the gray value. Assuming that the gray level of an image is
1∼N, and the pixel of the picture in the gray level iis m1,
then the total pixels can be expressed as
M�
N
i�1
mi.(10)
e probability calculation accords with equation (11)
when the value of gray level is i.
Ci�mi
M.(11)
In the above equation, Cirepresents the obtained
probability. If the gray value limit of the image is set to k, the
pixels of the image can be divided into two gray levels.
Equations (12) and (13) signify the calculation process.
P0�1,2,3,..., k
{ },(12)
P1�k+1, k +2,. . . , N
{ }.(13)
Moreover, equation (14) denotes the calculation of the
total gray level of the pixels of the image.
β�
N
i�1
Ci·i, (14)
where P0and P1represent the values of gray levels of the
image background and the target image, respectively, and β
is the total values of gray levels of the image. e average gray
level about P0can be computed as
β0�
k
i�1
Ci·i. (15)
Equation (16) demonstrates the pixel calculation under
the average gray level.
M0�
k
i�1
mi.(16)
e average gray level of P1can be computed as
β1�β−β0.(17)
Equation (18) expresses the pixel calculation under the
average gray level.
M1�M−M0.(18)
Equations (19) and (20) compute the ratio between the
background and the target image
ρ0�
k
i�1
Ci�ρ(k),(19)
ρ1�1−ρ(k).(20)
e processing on P0and P1can be computed using
equations (21) and (22), respectively.
β0�β(v)
ρ(k),(21)
β1�[β−β(k)]
[β−β(k)].(22)
e computation of the total average value of the pro-
cessed image is as follows:
β�ρ0β0+ρ1β1.(23)
Equation (24) computes the variance between species P0
and P1.
σ2(k) � ρ0β−β0
2+ρ1β−β1
2�ρ0ρ1β0−β1
2.(24)
e processed image is the best object for analysis. After
analysis, the risks in the process of college students’
physical education can be evaluated to guarantee their
physical safety [19].
3. Analysis of Factors Causing Sports Injuries
With the increase of people’s exercise in today’s society,
how to exercise scientifically and healthily has attracted
much attention. erefore, sports injury risk assessment
and monitoring systems have attracted more and more
attention in terms of real-time, flexibility, intelligence, and
other aspects. It is indispensable to conduct a risk as-
sessment in the process of implementing high-intensity
physical education in colleges. To explore the sports injury
assessment process, it is essential to identify the factors that
may cause sports injuries to college students during sports
activities [20].
e identification of the causes of injury is an important
step in injury prevention as this can be used to develop active
injury prevention programs. Sports professionals need to
know why some athletes may be at risk of injury risk factors
and how injuries occur to understand the causes of sports
injuries. Sports injuries are rarely due to a single factor, and
can generally be attributed to an association of circum-
stances [21]. ese injury risk factors can be categorized into
extrinsic and intrinsic injury risk. e extrinsic risk factor
mainly includes human factors (e.g. opponents, teammates),
sports factors (e.g. rules, referees, coaching), and environ-
mental factors such as weather, ice conditions, floor and turf
type, and playing surface. e internal risk factors mainly
include age, sex, body composition, skill level, psychological
factors, and physical fitness. Interaction between the ex-
trinsic and intrinsic risk factors may cause a student to be
more or less prone to injury. A combination of external and
internal risk factors acting concurrently puts students at a
4Computational Intelligence and Neuroscience
higher risk for injury [22]. Figure 2 lists the factors that may
cause sports injuries to students in the process of obtaining a
college sports education.
is study first recognizes the influencing factors, then
analyzes the injury status of students according to the impact
of different factors based on the occurrence of risk status,
and finally formulates corresponding guidelines for college
sports education according to the results to guarantee stu-
dents’ physical safety in sports [23].
Figure 3 displays the specific process of risk identifica-
tion. is implies that, in the identification of sports injury
risk, first, it is necessary to monitor the physical charac-
teristics of students participating in sports to confirm
whether they have sports injuries. If not, other students need
to be monitored. If yes, the causes of sports injuries in
students are analyzed and certain rules are formulated
according to the causes of injuries to prevent the recurrence
of such sports injuries again [22, 23]. In this study, two
groups of students, 30 in each group, were monitored for
sports injuries through visual sensing techniques, and 30
students with sports injuries were selected to analyze the
factors of injuries. Finally, relevant suggestions were put
forward according to the results.
4. Comprehensive Analysis
4.1. Detection of Students’ Sports Injuries. Sports injuries are a
composite emergent phenomenon. Using visual sensing
techniques, the sports injuries of college students can be
evaluated. It can be used to accurately check whether students
have sports injuries, to effectively guarantee students’ physical
and mental health, and to comprehensively improve the quality
of physical education teaching in colleges. Figure 4 manifests
the proportion of sports injuries suffered by college students.
It can be seen that, by checking whether 30 people in each
group have sports injuries and checking their body shape and
physical characteristics through visual sensing techniques,
different degrees of sports injuries are found in each sports
event. Among them, the number of sports injuries in ball
games is the largest in terms of the number of the two groups.
A total of 28 students have suffered sports injuries of varying
degrees in ball games. A total of 35 students have suffered
Risk Factors of Sports Injury
in Colleges and Universities
Student’s
Self-factors
Psychology
Body
Skill
Health
Physical Fitness
School
Management
Self-Management
Teacher
Management
Family Attitude
Social Attitude
Time
Weather
Site
Mental State
Mental Quality
External
Environmental
Factors
Management
Outside
Attitude
Others
Figure 2: Factors causing sports injury in colleges.
Computational Intelligence and Neuroscience 5
sports injuries of varying degrees in the horizontal bar. e
number of sports injuries from the long jump and high jump
is the least, and the total number is 11. It implies that the
evaluation of sports injuries of college students is necessary.
rough an analysis of sports injuries, the problems faced by
most students in sports can be detected. Figure 5 signifies the
comparison between the actual results and the results in the
students’ sports injury detection.
Figure 5 reveals that, in the comparison between the
detected results and the actual results of the two groups, the
error in the detected results of group 1 is about ±2, and the
detected results of two movements are completely consistent
with the actual results. e error in the detected results of
group 2 is about ±3, of which there is one movement, and the
detected results are completely consistent with the actual
results. Hence, by analyzing the images of students’ body
shapes and characteristics through visual sensing tech-
niques, the students’ having sports injuries can be effectively
verified.
4.2. Analysis of Factors Involved in Sports Injuries.
Further analysis of the factors of sports injuries reveals that
the detected results are consistent with the actual results,
which can be used to put forward constructive normative
opinions on college students’ sports education, improve
students’ comprehensive quality in sports, and provide
guidelines for the improvement of sports education quality.
Figure 6 manifests the self-factors of sports injuries in the
two groups of students.
Figure 6 reveals that, among the self-factors (intrinsic
factors) S (skill), PF (physical fitness), OI (old injuries), MQ
(mental quality), and MS (mental state) of sports injuries in
students, physical fitness has the greatest impact on sports
injuries. In the test results, the numbers of sports injuries
caused by the poor physical fitness of members were 5 and 6
in the two groups, respectively. e factor with the lowest
comprehensive impact is the mental state of students. In the
test results, the numbers of sports injuries caused by mental
Start
Check the student's body
Whether a sports injury
Has Occurred?
Look for the factors of sports injuries
e intensity of the sports injury
Finish
No
Yes
Figure 3: Risk identification of sports injuries.
Total
Group 1
Group 2
Long Jump
Horizontal Bar
Ball Games
Other
Run
Project
0
5
10
15
20
25
30
35
Number of People
Figure 4: Sports injury detection of College Students.
6Computational Intelligence and Neuroscience
state were 1 and 0 in the two groups, respectively. Physical
quality is very important in sports, and psychological factors
will also have a certain impact. erefore, college physical
education needs to be comprehensively improved. Figure 7
displays the external (extrinsic factors) factors of sports
injury in the two groups of students.
Figure 7 indicates that, among the external factors T
(time), W (weather), S (site), M(management), and A
(attitude) of sports injuries in the two groups, the weather is
the most influential factor. In the test results, the number of
sports injuries caused by weather is 12 and 13 in the two
groups, respectively, and the lowest comprehensive im-
pression factor is the students’ attitude to the outside world.
In the test results, the numbers of sports injuries due to
external attitudes were 4 and 2, respectively in the two
groups. More attention needs to be paid to the weather
conditions in the process of sports so that college physical
education can also be carried out scientifically. In the pre-
diction of the external environment, the image analysis of
students’ body shapes and characteristics is carried out by
using visual sensing techniques, and there are ideal results of
the comparison between the obtained results and the actual
results. Figure 8 displays the errors in sports injuries de-
tection of college students.
Figure 8 indicates that, in the analysis of the error factors in
sports injuries, the detection error of self-factors is about ±2,
e Actual Number
Number of People Tested
Long Jump
Horizontal Bar
Ball Games
Other
Run
0
2
4
6
8
10
12
14
16
18
Number of People
(a)
e Actual Number
Number of People Tested
Long Jump
Horizontal Bar
Ball Games
Other
Run
0
2
4
6
8
10
12
14
16
Number of People
(b)
Figure 5: Comparison between actual sports injuries and detected sports injuries: (a) the comparison between actual sports injuries and
detected sports injuries in group 1 and (b) the comparison between actual sports injuries and detected sports injuries in group 2.
Actual
Detect
PF OI MQ MSS
0
1
2
3
4
5
6
Number of People
(a)
Actual
Detect
PF OI MQ MSS
0
1
2
3
4
5
6
7
Number of People
(b)
Figure 6: Self-factors of sports injury in colleges: (a) the self-factors of group 1 and (b) the self-factors of group 2.
Computational Intelligence and Neuroscience 7
while the detection error of external factors is between −3 and
2. It is close to the results of the sports injuries obtained by
analyzing the characteristics of students’ body shapes through
the visual sensing technique and the actual sports injuries.
e study analyzed the body shape and characteristics of
college students using visual sensing, image recognition, and
image processing techniques. e purpose is to detect college
students’ sports injuries and analyze the influencing factors.
It comprehensively evaluates the risk of college sports in-
juries through detection and analysis. It is found that sports
injuries in colleges occur in various sports events. It is es-
sential to improve the existing sports teaching mode, reduce
the risk of sports injuries in sports education, and guarantee
students with safety in sports education. Among students’
self-factors, colleges should focus on basic physical
education, enhance students’ physical fitness and sports
skills training, and also provide psychological counseling
and education for students. en, college administration
should also cooperate with parents to vigorously support
students’ sports training, build good sports venues, manage
students’ sports education, and provide proper time for
sports. ese aspects can provide a basic guarantee for
preventing sports injuries in college sports education.
5. Conclusion
Injuries are common in college sports and can have sig-
nificant physical, psychosocial, and financial consequences.
Identification of sports injury risk factors and their rela-
tionship is, therefore, a key component in reducing future
Actual
Detect
0
2
4
6
8
10
12
14
Number of People
WSMAT
(a)
Actual
Detect
WSMAT
0
2
4
6
8
10
12
14
Number of People
(b)
Figure 7: External factors of sports injury in colleges: (a) group 1 and (b) group 2.
Group 1
Group 2
-2.5
-2
-1.5
-1
-0.5
0
0.5
1
1.5
2
2.5
Error
PF OI MQ MSS
(a)
Group 1
Group 2
PF OI MQ MSS
-4
-3
-2
-1
0
1
2
3
Error
(b)
Figure 8: e number of error factors in sports injuries of college students: (a) self-factors and (b) external factors.
8Computational Intelligence and Neuroscience
injuries in sports. In this study, an analysis was made on the
risk of physical injuries to college students to guarantee the
physical safety of students in sports and improve the quality
of physical education. en, a study is carried out on the
occurrence of physical injury risk through visual sensing
techniques, and an investigation is made into the charac-
teristics of physical injury risk in colleges. It is found that
among the intrinsic sports risk factors, physical fitness has
the greatest impact on sports injuries, whereas in the case of
extrinsic factors, unfavorable weather is the main cause of
sports injuries. Finally, by comparing the detected results
with the actual results, it is concluded that the image rec-
ognition and processing techniques can accurately identify
the occurrence of sports injuries in college students and can
effectively identify the factors that cause sports injuries. e
present work provides technical support for the detection of
sports injuries in colleges and contributes to the improve-
ment of sports education quality in colleges.
Data Availability
e data used to support the findings of this study are
available from the corresponding author upon request.
Conflicts of Interest
e authors declare that there are no conflicts of interest.
References
[1] C. Xin and X. Wang, “Research on the application of college
physical education teaching mode in the cloud computing
environment,” Journal of Physics: Conference Series, vol. 1624,
no. 2, Article ID 022068, 2020.
[2] X. Shi, X. Li, and Y. Wu, “e Application of computer-aided
teaching and mobile Internet terminal in college physical
education,” Computer-Aided Design, vol. 18, no. 23,
pp. 163–174, 2021.
[3] H. Kim, T. Song, S. Lim, H. W. Kohl, and H. Han, “Physical
activity engagement outside of college physical education:
application of the transtheoretical model,” American Journal
of Health Behavior, vol. 45, no. 5, pp. 924–932, 2021.
[4] S. A. Yu, “Application of computer information technology in
college physical education using fuzzy evaluation theory,”
Computational Intelligence, vol. 37, no. 3, pp. 1181–1198, 2021.
[5] H. Zhou, “Research on the Function of Computer Aided
Teaching in College Physical Education,” Conference Series,
vol. 1992, no. 2, Article ID 022107, 2021.
[6] A. Zadeh, D. Taylor, M. Bertsos, T. Tillman, N. Nosoudi, and
S. Bruce, “Predicting Sports Injuries with Wearable Tech-
nology and Data Analysis,” Information Systems Frontiers,
vol. 23, no. 4, pp. 1023–1037, 2020.
[7] W. H. Meeuwisse, H. Tyreman, B. Hagel, and C. Emery, “A
dynamic model of etiology in sport injury: the recursive
nature of risk and causation,” Clinical Journal of Sport
Medicine, vol. 17, no. 3, pp. 215–219, 2007.
[8] A. Hulme and C. F. Finch, “From monocausality to system
thinking: a complementary and alternative conceptual ap-
proach for better understanding the development and pre-
vention of sports injury,” Inj Epidemiol, vol. 2, no. 1, p. 31,
2015.
[9] F. Rao, “Experimental study on alleviating sports injury
through data screening of functional motor biological im-
ages,” Journal of Healthcare Engineering, vol. 2021, pp. 1–6,
Article ID 8099451, 2021.
[10] H. V. Eetvelde, L. D. Mendonca, C. Ley, R. Seil, and T. Tischer,
“Machine learning methods in sports injury prediction and
prevention: a systematic review,” Journal of Experimental
Orthopedics, vol. 8, no. 1, 2021.
[11] W. Yi and F. Fang, “e design and realization of the
management system of college physical education under the
network environment,” Journal of Physics: Conference Series,
vol. 1345, no. 5, Article ID 052034, 2019.
[12] Y. Jinhai, “Research on the application of big data ecology in
college physical education and training,” IOP Conference
Series: Materials Science and Engineering, vol. 631, no. 5,
Article ID 052044, 2019.
[13] M. Vaughn, J. W. Hur, and J. Russell, “Flipping a college
physical activity course: impact on knowledge, skills, and
physical activity,” Journal of Pedagogical Research, vol. 3,
no. 3, pp. 87–98, 2019.
[14] C. Feng, “Research on the application of computer virtual
reality technology in college physical education teaching,”
Journal of Physics: Conference Series, vol. 1648, no. 2, Article
ID 022035, 2020.
[15] C. Deng, Z. Tang, X. Li, and Z. Zhao, “Construction and
application of web-based resource repository of college
physical education,” Journal of Physics: Conference Series,
vol. 1575, no. 1, Article ID 012024, 2020.
[16] P. Lei, “Research on the quality of online teaching of college
physical education courses under the impact of the epidemic,”
Journal of Frontiers in Educational Research, vol. 1, no. 4,
pp. 121–126, 2021.
[17] J. Li, “Application research of vision sensor in material sorting
automation control system,” IOP Conference Series: Materials
Science and Engineering, vol. 782, no. 2, Article ID 022074,
2020.
[18] R. Xiao, Y. Xu, Z. Hou, C. Chen, and S. Chen, “An adaptive
feature extraction algorithm for multiple typical seam
tracking based on vision sensor in robotic arc welding,”
Sensors and Actuators A: Physical, vol. 297, no. 34, Article ID
111533, 2019.
[19] J. Fan, F. Jing, L. Yang, T. Long, and M. Tan, “A precise seam
tracking method for narrow butt seams based on structured
light vision sensor,” Optics & Laser Technology, vol. 109,
no. 14, pp. 616–626, 2019.
[20] Y. Han, J. Fan, and X. Yang, “A structured light vision sensor
for on-line weld bead measurement and weld quality in-
spection,” International Journal of Advanced Manufacturing
Technology, vol. 106, no. 5, pp. 2065–2078, 2020.
[21] J. Du, D. Xie, Q. Zhang et al., “A robust neuromorphic vision
sensor with optical control of ferroelectric switching,” Nano
Energy, vol. 89, no. 12, Article ID 106439, 2021.
[22] P. Bhowmik, M. J. H. Pantho, and C. Bobda, “Bio-inspired
smart vision sensor: toward a reconfigurable hardware
modeling of the hierarchical processing in the brain,” Journal
of Real-Time Image Processing, vol. 18, no. 1, pp. 157–174,
2021.
[23] M. Oudah, A. Al Naji, and J. Chahl, “Hand gesture recog-
nition based on computer vision: a review of techniques,”
Journal of Imaging, vol. 6, no. 8, p. 73, 2020.
Computational Intelligence and Neuroscience 9
Available via license: CC BY 4.0
Content may be subject to copyright.
